{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.5245599746704102, "min": 1.5245599746704102, "max": 2.861053943634033, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 15680.099609375, "min": 15166.919921875, "max": 29300.052734375, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 9.88288688659668, "min": 0.4926242530345917, "max": 9.88288688659668, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2016.1090087890625, "min": 95.56910705566406, "max": 2016.1090087890625, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06963197084385718, "min": 0.06523262478149085, "max": 0.07072075137515568, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3481598542192859, "min": 0.2609304991259634, "max": 0.3481598542192859, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23998304500299344, "min": 0.11192102356147313, "max": 0.302929982250812, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1999152250149672, "min": 0.4476840942458925, "max": 1.5146499112540601, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 21.29090909090909, "min": 3.2954545454545454, "max": 21.29090909090909, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1171.0, "min": 145.0, "max": 1171.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.29090909090909, "min": 3.2954545454545454, "max": 21.29090909090909, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1171.0, "min": 145.0, "max": 1171.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700131158", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700131405" }, "total": 246.230720755, "count": 1, "self": 0.4262102499999969, "children": { "run_training.setup": { "total": 0.044120394999993096, "count": 1, "self": 0.044120394999993096 }, "TrainerController.start_learning": { "total": 245.76039011, "count": 1, "self": 0.43380661099757845, "children": { "TrainerController._reset_env": { "total": 7.860490174999995, "count": 1, "self": 7.860490174999995 }, "TrainerController.advance": { "total": 237.38101356600242, "count": 9137, "self": 0.13481482100161202, "children": { "env_step": { "total": 237.2461987450008, "count": 9137, "self": 163.09791945400002, "children": { "SubprocessEnvManager._take_step": { "total": 74.01034710000175, "count": 9137, "self": 0.7222583850015667, "children": { "TorchPolicy.evaluate": { "total": 73.28808871500019, "count": 9137, "self": 73.28808871500019 } } }, "workers": { "total": 0.13793219099903808, "count": 9137, "self": 0.0, "children": { "worker_root": { "total": 244.93593505300163, "count": 9137, "is_parallel": true, "self": 122.74732151900261, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004786378999995122, "count": 1, "is_parallel": true, "self": 0.003376985999977933, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014093930000171895, "count": 10, "is_parallel": true, "self": 0.0014093930000171895 } } }, "UnityEnvironment.step": { "total": 0.06540525500000172, "count": 1, "is_parallel": true, "self": 0.0006872099999952752, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003849510000009104, "count": 1, "is_parallel": true, "self": 0.0003849510000009104 }, "communicator.exchange": { "total": 0.062340755999997555, "count": 1, "is_parallel": true, "self": 0.062340755999997555 }, "steps_from_proto": { "total": 0.001992338000007976, "count": 1, "is_parallel": true, "self": 0.0004014980000022206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015908400000057554, "count": 10, "is_parallel": true, "self": 0.0015908400000057554 } } } } } } }, "UnityEnvironment.step": { "total": 122.18861353399902, "count": 9136, "is_parallel": true, "self": 5.305627638003386, "children": { "UnityEnvironment._generate_step_input": { "total": 2.74167883599452, "count": 9136, "is_parallel": true, "self": 2.74167883599452 }, "communicator.exchange": { "total": 96.49714835600025, "count": 9136, "is_parallel": true, "self": 96.49714835600025 }, "steps_from_proto": { "total": 17.64415870400086, "count": 9136, "is_parallel": true, "self": 3.265575316005112, "children": { "_process_rank_one_or_two_observation": { "total": 14.378583387995747, "count": 91360, "is_parallel": true, "self": 14.378583387995747 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002724039999861816, "count": 1, "self": 0.0002724039999861816, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 235.61221104902194, "count": 235118, "is_parallel": true, "self": 5.179380271013088, "children": { "process_trajectory": { "total": 133.16772174900876, "count": 235118, "is_parallel": true, "self": 132.8062751170088, "children": { "RLTrainer._checkpoint": { "total": 0.36144663199996785, "count": 2, "is_parallel": true, "self": 0.36144663199996785 } } }, "_update_policy": { "total": 97.26510902900009, "count": 45, "is_parallel": true, "self": 34.77733833699915, "children": { "TorchPPOOptimizer.update": { "total": 62.487770692000936, "count": 2289, "is_parallel": true, "self": 62.487770692000936 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08480735400002004, "count": 1, "self": 0.0008673900000530921, "children": { "RLTrainer._checkpoint": { "total": 0.08393996399996695, "count": 1, "self": 0.08393996399996695 } } } } } } }